Meta
Llama 3.3 Instruct 70B is a Meta Llama 3 family model, part of Meta's widely deployed open-weight LLM series for assistants, retrieval, coding, and self-hosted applications. The profile helps compare this specific size and instruction variant with newer open and proprietary models in the local snapshot.
Introducing Meta Llama 3Rank #462 across 526
Rank #331 across 436
Rank #155 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 8.6 | #462 |
| Artificial Analysis Coding Index | coding | 10.7 | #331 |
| Artificial Analysis Math Index | math | 7.7 | #236 |
| MMLU-Pro | reasoning | 71.3% | #212 |
| reasoning |
| 49.8% |
| #363 |
| Humanity's Last Exam | reasoning | 4.0% | #435 |
| LiveCodeBench | coding | 28.8% | #232 |
| SciCode | coding, reasoning | 26.0% | #328 |
| MATH-500 | math | 77.3% | #117 |
| AIME | math | 30.0% | #84 |
| Output Speed | speed | 101.2 tok/s | #133 |
| Time to First Token | speed | 0.61s | #71 |
| Blended Price | cost | $0.612/M | #155 |
| Input Price | cost | $0.580/M | #204 |
| Output Price | cost | $0.710/M | #112 |
| Value Index | cost, overall | 14.1 | #241 |